Posted on Reading Time: 3 minuteson
As described in the MEF Edge VIEW Blog post, MEF: End-to-End Slicing for 5G and Beyond, enterprises are increasingly considering using network slicing as part of their digital transformation. One emerging category of use cases for network slicing, in combination with 5G, is based on the increasing use of AI/ML, which is compute- and storage-intensive. The combination of very low-latency, wireless connectivity available with 5G, high levels of compute and storage in Multi-Edge Access Computing (MEC), and the latest capabilities of AI/ML, is opening up a wide range of new use cases and opportunities for both enterprises and service providers.
Okinawa, one of Japan’s most famous beach and marine resorts, is increasingly subject to criminal activity on its beaches, as well as the intrusion of dangerous or harmful marine life in nearby waters. AI/ML is being focused as the way to both identify human suspects among beachgoers, as well as problematic sealife, like the invasive lionfish as well as sharks.
This use case incorporates real-time high-definition video, streamed at 100 Mbps over 5G from land-based cameras, as well as cameras on airborne and undersea drones, to compute and storage facilities running AI/ML in a nearby MEC. Instead of human operators constantly monitoring video screens, which is expensive and error-prone, AI/ML is used to automatically flag potential problems to the relevant safety personnel, who take appropriate action.
For each one of multiple video stream feeds to AI/ML, mission-critical drone control signals, and high-quality audio for live announcements to both the public and safety personnel in the area to work effectively, latency has to be kept to a guaranteed maximum of a few milliseconds in this use case. Hence, in this application, the ability to create high-performance slices over 5G is essential.
Furthermore, the slices will likely traverse more than the 5G service in order to get to the MEC—for example, over Carrier Ethernet or MPLS. Performance and quality assurance of end-to-end slices is achieved, not only by slicing and quality assurance within each connectivity domain and service provider, but also by connecting slices between domains and service providers. It also requires a mechanism for slice selection control at the orchestration layer.
Also read our other blog post: Factory Automation and the Next Generation Data Center.
Read more about MEF 3.0 PoC (138) E2E Slicing for Extreme Services.
MEF 3.0 PoC (138) E2E Slicing for Extreme Services was presented at the MEF PoC Showcase on 25 February 2021. To see the presentation on-demand, Register for the PoC Showcase.
About MEF’s Proof of Concept Program & Showcase
The MEF 3.0 Proof of Concept program effectively fosters innovation, seeds new MEF standards and projects, and accelerates our existing work within the ICT industry by providing our members—including service providers, technology suppliers, and other stakeholders within the ICT industry—the opportunity to collaborate on MEF 3.0-based use cases throughout the year.
Initiated by MEF members and facilitated by MEF staff, each MEF 3.0 PoC receives a unique, identifying number that remains unchanged as its title and messaging evolves over the life of the project.
PoC work is highlighted in public showcases and award presentations that explore individual Proofs of Concept.
Hiroki is a senior research engineer of NTT network technology laboratories, and working in NTT and NTT group companies for more than 12 years. Hiroki is currently engaged in future network architecture related to network slicing across 5G and WAN. Before that, he had worked for NTT docomo, and he was engaged in network architecture design and planning regarding NFV commercial service introduction and promotion.